#VoxxedDaysCERN26

Tired of juggling Jira, Confluence, GitLab, and Slack/Mattermost? What if one AI could search tickets, find docs, check PRs, and summarize discussions, while keeping data on-premise and avoiding subscription costs?
I'll show how to build this using the Model Context Protocol (MCP), an open standard for AI-tool integration, now under the Linux Foundation and adopted by OpenAI, Google, and Microsoft.

What the audience will see:
MCP Introduction : What is MCP, how old is it, who's driving it forward (Anthropic, growing community), and why it matters - the "USB-C for AI tools."
Architecture and Implemetation : How MCP clients, servers, and the protocol work together. The local stack: Ollama + Open WebUI + mcpo proxy connecting to MCP servers for Atlassian, GitLab, and Obsidian.

Demo : Real queries across systems: Searching tickets, finding docs, checking repos

Key Takeaways :
Basic understanding of MCP protocol
See a real POC connecting to enterprise tools
Blueprint of the architecture to experiment with
Target audience: Engineers, developers, curious technologists, team leads, anyone interested in practical AI integration.

Devoxx

A conference talk introducing Model Context Protocol (MCP), an open standard created by Anthropic in late 2024 and donated to the Linux Foundation. MCP solves the problem of connecting AI host applications to external tools and services without writing custom integrations for each one. The talk explains the three-component architecture (host app, MCP client, MCP servers), demonstrates a live workflow where an AI reads messages from Mattermost and automatically creates Jira tickets from identified issues, and previews future possibilities like interactive UI components rendered within the host app. The speaker also mentions using MCP with Obsidian for automatic note-taking.

One AI Chat to Rule Them All: Connecting Enterprise Tools with MCP by Karthik Sayapparaju